A Unified Algebraic Approach to 2-D and 3-D Motion Segmentation 2006. 6. 9 (Fri) Young Ki Baik, Computer Vision Lab.
Feb 08, 2016
A Unified Algebraic Approach to 2-D and 3-D Motion Segmentation
2006. 6. 9 (Fri)Young Ki Baik, Computer Vision Lab.
2
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• References• A Unified Algebraic Approach to 2-D and 3-
D Motion Segmentation• Rene Vidal and Yi Ma (ECCV 2004)
• Generalized Principal Component Analysis (GPCA)
• Rene Vidal, Yi Ma, et. al. (PAMI 2005)
3
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• Contents• Introduction• GPCA• 2-D motion segmentation• 3-D motion segmentation• Experimental results• Summary
4
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• Introduction (Motion segmentation)• Target
• 2D, 3D motion segmentation
• Problem statement• Most previous work
Iterative approach (EM, RANSAC, etc.) Manual or random initial value.
Cause of divergence or bad results
• Proposed algorithm• Good initial value using non-iterative
algebraic method
5
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• Introduction (This paper)• Contribution
• Applying GPCA to 2D, 3D motion segmentation problem
• Condition• Subspaces are all linear.• Known correspondences• Known number of subspace (class)
6
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• GPCA (Generalized PCA)• GPCA treats heterogeneous data and
multiple subset with different linear model.
7
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• GPCA (Generalized PCA)• Find the basis of each subspace which
orthogonal to data x
b
x
SforT xbx 0
SdatabasissubspaceS
:::
xb
8
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• GPCA (Generalized PCA)• A homogeneous polynomial of degree n
• The mixture of subspaces can be linearly fitting general polynomial to the given data.
• Example• Number of subspace n = 2• Vector size k = 3
xcx nT
n vp mapVeronesev
polynomialpsetdata
subspaceofnumbern
n
n
::
: :
x
321 ,, xxxx
0236325
224313212
2112 xcxxcxcxxcxxcxcxp
9
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• GPCA (Generalized PCA)• Find the basis from derivatives of the
polynomials with y on the S
b
y
by ~nDp
S databasissubspaceS
:::
yb
10
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• GPCA (Algorithm)• Fitting polynomials to data lying in multiple
subspaces
• Obtaining basis of each subspace by polynomial differentiation
• Choosing data per subspace by using basis
by ~nDp
xcx nT
n vp 0 Ac
SforT xbx 0
11
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• Motion segmentation• Notation
• Let be a vector in or .z KR KC
n
in
TTin vp
1
zczbz
zKnN
vector ofdimension :subspace ofnumber :data ofnumber :
mapVeronesev
polymonialppofvectortcoefficien
subspacethiofbasis
n
n
n
i
::
: :
cb
12
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• 2D Motion segmentation• Translation case
• Under 2-d translation motion model, the two images are related by on out of n possible 2-d translation .
iTxx 12
222
21 ,, RTRxRx i
nii 12
RT
2
12
01
1 Cxx
Tzb
iTi
2212 , CTCxx i
z
1
231
21
13
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• 2D Motion segmentation• Translation case
• Finding coefficient c (fitting polynomial)
jbaj011
12 xxz
0201 622
5432122 abjcbacjbcacjccvp zcz
06 cAN
z2psvd
14
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• 2D Motion segmentation• Translation case
• Finding basis (using polynomial differentiation)
zzz 2
2pDp
i
Dpi yzzb
2~ 0iTi yb
zz
z n
n
alln Dp
py
minarg 0 lastI
1
1
ImRe
i
ii b
bT
15
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• 2D Motion segmentation• Translation case
• Segmentation
njjTn
allSn zzb
n minargN~1 i for
end
16
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• 2D Motion segmentation• Affine motion case
• In this case, we assume that the images are related by a collection on n 2-D affine motion models .
111
232221
13121112
xxAx
aaaaaa
i
nii 132
RA
111
2313221221111
2
xxx jaajaajaaaTi
01
1
2
12
11
x
xx
zb Ti
Ti a
4Cz
17
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• 3D Motion segmentation• Epipolar constraint • Homography
18
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• Experimental results
19
A Unified Algebraic Approach to 2D and 3D Motion Segmentation
• Summary• Contribution
• Applying GPCA to 2D, 3D motion segmentation problem
• Good initial value using non-iterative algebraic method
• Limitation• Linear subspace• Known correspondences and number of subspace • If subspace is increased, then computational
complexity will be exponentially increased.